Claude Code Plugins Directory

A curated directory of high-quality plugins for Claude Code.

⚠️ Important: Make sure you trust a plugin before installing, updating, or using it. Anthropic does not control what MCP servers, files, or other software are included in plugins and cannot verify that they will work as intended or that they won't change. See each plugin's homepage for more information.

Structure

• /plugins - Internal plugins developed and maintained by Anthropic
• /external_plugins - Third-party plugins from partners and the community

Installation

Plugins can be installed directly from this marketplace via Claude Code's plugin system.

To install, run /plugin install {plugin-name}@claude-plugins-official

or browse for the plugin in /plugin > Discover

Heroku Deployment

You can host your own Claude Code plugin registry on Heroku. This is useful for private plugin catalogs, custom configurations, or when you want to expose a focused set of plugins (e.g. cursor and hermes-agent) to your team.

One-click deploy

Manual deploy

# 1. Fork / clone this repo
git clone https://github.com/Primosphered/claude-plugins-official.git
cd claude-plugins-official

# 2. Create a Heroku app
heroku create my-claude-registry

# 3. Configure environment variables
heroku config:set ENABLED_PLUGINS="cursor,hermes-agent"
heroku config:set ANTHROPIC_API_KEY="sk-ant-..."   # optional — for agent features
heroku config:set LLM_PROVIDER="anthropic"

# 4. Deploy
git push heroku main

# 5. Verify
curl https://my-claude-registry.herokuapp.com/health

Environment variables

Variable	Default	Description
ENABLED_PLUGINS	(all)	Comma-separated list of plugin names to expose. Set to cursor,hermes-agent to expose only those two.
ANTHROPIC_API_KEY	—	Required for plugins that invoke Claude models (e.g. hermes-agent).
LLM_PROVIDER	anthropic	LLM backend: anthropic, openai, or custom.
CUSTOM_LLM_ENDPOINT	—	Base URL for a custom LLM endpoint (when LLM_PROVIDER=custom).
PORT	3000	HTTP port — set automatically by Heroku.

Copy .env.example to .env for local development.

API endpoints

Endpoint	Description
GET /health	Health check
GET /marketplace.json	Full (or filtered) plugin manifest — point Claude Code here as a custom registry
GET /plugins	JSON list of enabled plugins with name, description, and category
GET /plugins/:name	Metadata for a single plugin

Point Claude Code at your registry

/plugin set registry https://my-claude-registry.herokuapp.com/marketplace.json

Focus plugins

The default ENABLED_PLUGINS value exposes two plugins optimised for LLM-agent workflows:

• cursor — Generate and manage Cursor IDE rules (.cursorrules / .cursor/rules/*.mdc) tailored to your codebase. Install with /plugin install cursor@claude-plugins-official.
• hermes-agent — Deep reasoning agent with structured chain-of-thought analysis, multi-step planning, and safe execution for complex engineering tasks. Install with /plugin install hermes-agent@claude-plugins-official.

Contributing

Internal Plugins

Internal plugins are developed by Anthropic team members. See /plugins/example-plugin for a reference implementation.

External Plugins

Third-party partners can submit plugins for inclusion in the marketplace. External plugins must meet quality and security standards for approval. To submit a new plugin, use the plugin directory submission form.

Plugin Structure

Each plugin follows a standard structure:

plugin-name/
├── .claude-plugin/
│   └── plugin.json      # Plugin metadata (required)
├── .mcp.json            # MCP server configuration (optional)
├── commands/            # Slash commands (optional)
├── agents/              # Agent definitions (optional)
├── skills/              # Skill definitions (optional)
└── README.md            # Documentation

License

Please see each linked plugin for the relevant LICENSE file.

Documentation

For more information on developing Claude Code plugins, see the official documentation.